Making Semantic Search and RAG Real - How to Build a Production-Ready Application
AWS Events via YouTube
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Learn the Skills Netflix, Meta, and Capital One Actually Hire For
Overview
Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Discover in this AWS re:Invent 2023 conference talk how to build production-ready applications incorporating semantic search and Retrieval Augmented Generation (RAG). Explore the complexities of implementing private data retrieval with Large Language Models (LLMs) at scale, moving beyond basic kNN search implementations. Learn to develop robust search experiences that prioritize simplicity, repeatability, and security while implementing elegant APIs capable of managing data across various stores, middleware, and internal applications. Master the implementation of essential enterprise features including Role-Based Access Control (RBAC), High Availability (HA), and Disaster Recovery (DR) across cloud and on-premises environments. Gain valuable insights from Elastic, an AWS Partner, on operationalizing enterprise-grade AI search solutions with LLMs, ensuring your applications meet production-level requirements for performance, security, and scalability.
Syllabus
AWS re:Invent 2023 - Making semantic search & RAG real: How to build a prod-ready app (AIM201)
Taught by
AWS Events